Initial model upload with model card

README.md

@@ -0,0 +1,43 @@
+---
+license: apache-2.0
+datasets:
+- stapesai/ssi-speech-emotion-recognition
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+pipeline_tag: audio-classification
+---
+
+# Multimodal Emotion Speech Recognition
+
+## Model Description
+This model performs emotion recognition from speech using a multimodal approach, utilizing:
+- **Audio Model**: Wav2Vec2 Base
+- **Text/Context Model**: RoBERTa Base
+
+## Dataset
+- **Dataset Name**: [stapesai/ssi-speech-emotion-recognition](https://huggingface.co/datasets/stapesai/ssi-speech-emotion-recognition)
+
+## Evaluation Results
+
+### Classification Report
+```
+              precision    recall  f1-score   support
+
+         ANG       0.96      0.90      0.93        30
+         CAL       0.00      0.00      0.00         0
+         DIS       0.86      0.95      0.90        20
+         FEA       0.78      0.67      0.72        27
+         HAP       0.84      0.79      0.81        33
+         NEU       0.89      0.96      0.92        25
+         SAD       0.78      0.95      0.86        19
+         SUR       0.88      0.78      0.82         9
+
+    accuracy                           0.85       163
+   macro avg       0.75      0.75      0.75       163
+weighted avg       0.86      0.85      0.85       163
+```
+
+**Overall Accuracy**: 0.85

labels.json

@@ -0,0 +1,10 @@
+{
+  "ANG": 0,
+  "CAL": 1,
+  "DIS": 2,
+  "FEA": 3,
+  "HAP": 4,
+  "NEU": 5,
+  "SAD": 6,
+  "SUR": 7
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71cbc4ca6119fb237ad9a6c3c52485b9639fb045a127925e00e7dc82e0829680
+size 879376827

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/events.out.tfevents.1767969866.MSI.24952.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a91cdddf3ccfc112d6a828b6b242063421b25cc2f951d312012916ec2e2fbf
+size 42689

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}